| STRATEGY LIBRARY DATASET RULES | |
| Strategy documents are knowledge assets, not ordinary prose blobs. The | |
| extraction pipeline should preserve: | |
| - strategy name | |
| - market/instrument | |
| - timeframe | |
| - session | |
| - setup conditions | |
| - entry conditions | |
| - invalidation conditions | |
| - stop-loss logic | |
| - take-profit logic | |
| - position sizing/risk rules | |
| - confirmation requirements | |
| - no-trade conditions | |
| - examples and counterexamples | |
| When a document contains rules, the dataset should not invent missing rules. | |
| When a rule is ambiguous, preserve the ambiguity in the source text or flag it | |
| for review. | |
| A strategy-library knowledge-base row should be suitable for retrieval and | |
| should contain a coherent context chunk rather than an arbitrary cut through a | |
| table or rule. | |
| For conversational fine-tuning, use instruction/input/response or the target | |
| chat format selected by the user. Do not fabricate a profitable trade outcome. | |
Xet Storage Details
- Size:
- 906 Bytes
- Xet hash:
- 98733fb8e5ffea294e980ae4bdd8c61e1ffb058e3c4aede955fc80aff17e530c
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.